{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A5C6JEI7JSOZFKMIKRAL4QADRC","short_pith_number":"pith:A5C6JEI7","schema_version":"1.0","canonical_sha256":"0745e4911f4c9d92a9885440be400388a48dff43860d82004d9457b8783a68e9","source":{"kind":"arxiv","id":"2503.10639","version":1},"attestation_state":"computed","paper":{"title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengqi Duan, Hao Li, Hao Tian, Hongsheng Li, Jifeng Dai, Kun Wang, LinJiang Huang, Rongyao Fang, Rui Zhao, Shilin Yan, Xihui Liu, Xingyu Zeng","submitted_at":"2025-03-13T17:59:59Z","abstract_excerpt":"Current image generation and editing methods primarily process textual prompts as direct inputs without reasoning about visual composition and explicit operations. We present Generation Chain-of-Thought (GoT), a novel paradigm that enables generation and editing through an explicit language reasoning process before outputting images. This approach transforms conventional text-to-image generation and editing into a reasoning-guided framework that analyzes semantic relationships and spatial arrangements. We define the formulation of GoT and construct large-scale GoT datasets containing over 9M s"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.10639","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"c084fade014dc7e25484b5522c995e944703ac57d3abf0f5bf0b17a6057bda72","abstract_canon_sha256":"32fb8343f7b43ce3d729bb992f1330bed5d44ec8dc0036a380a2fc8d430f4069"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:49.376208Z","signature_b64":"plAJM7LQ+NrjfqbuCtzEq7lyycONarYsMP+Bd8vmZAlWlxvSdThRNvJCWvfejLGuOM+byCNZp/Ur/vboeV4UCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0745e4911f4c9d92a9885440be400388a48dff43860d82004d9457b8783a68e9","last_reissued_at":"2026-07-05T10:30:49.375680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:49.375680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengqi Duan, Hao Li, Hao Tian, Hongsheng Li, Jifeng Dai, Kun Wang, LinJiang Huang, Rongyao Fang, Rui Zhao, Shilin Yan, Xihui Liu, Xingyu Zeng","submitted_at":"2025-03-13T17:59:59Z","abstract_excerpt":"Current image generation and editing methods primarily process textual prompts as direct inputs without reasoning about visual composition and explicit operations. We present Generation Chain-of-Thought (GoT), a novel paradigm that enables generation and editing through an explicit language reasoning process before outputting images. This approach transforms conventional text-to-image generation and editing into a reasoning-guided framework that analyzes semantic relationships and spatial arrangements. We define the formulation of GoT and construct large-scale GoT datasets containing over 9M s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10639","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.10639/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.10639","created_at":"2026-07-05T10:30:49.375751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10639v1","created_at":"2026-07-05T10:30:49.375751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10639","created_at":"2026-07-05T10:30:49.375751+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5C6JEI7JSOZ","created_at":"2026-07-05T10:30:49.375751+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5C6JEI7JSOZFKMI","created_at":"2026-07-05T10:30:49.375751+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5C6JEI7","created_at":"2026-07-05T10:30:49.375751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00920","citing_title":"GMO-E$^2$DIT: Grounded Multi-Operation Editing for E-Commerce Images","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00920","citing_title":"GMO-E$^2$DIT: Grounded Multi-Operation Editing for E-Commerce Images","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05031","citing_title":"MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04479","citing_title":"Evaluating Reasoning Fidelity in Visual Text Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14842","citing_title":"Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19852","citing_title":"Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02547","citing_title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","ref_index":256,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13609","citing_title":"Do-Undo Bench: Reversibility for Action Understanding in Image Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":255,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11400","citing_title":"UniPath: Adaptive Coordination of Understanding and Generation for Unified Multimodal Reasoning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20275","citing_title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10859","citing_title":"Masked Generative Transformer Is What You Need for Image Editing","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24625","citing_title":"Meta-CoT: Enhancing Granularity and Generalization in Image Editing","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23763","citing_title":"Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17761","citing_title":"Step1X-Edit: A Practical Framework for General Image Editing","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10454","citing_title":"AIM-Bench: Benchmarking and Improving Affective Image Manipulation via Fine-Grained Hierarchical Control","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07334","citing_title":"RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5C6JEI7JSOZFKMIKRAL4QADRC","json":"https://pith.science/pith/A5C6JEI7JSOZFKMIKRAL4QADRC.json","graph_json":"https://pith.science/api/pith-number/A5C6JEI7JSOZFKMIKRAL4QADRC/graph.json","events_json":"https://pith.science/api/pith-number/A5C6JEI7JSOZFKMIKRAL4QADRC/events.json","paper":"https://pith.science/paper/A5C6JEI7"},"agent_actions":{"view_html":"https://pith.science/pith/A5C6JEI7JSOZFKMIKRAL4QADRC","download_json":"https://pith.science/pith/A5C6JEI7JSOZFKMIKRAL4QADRC.json","view_paper":"https://pith.science/paper/A5C6JEI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10639&json=true","fetch_graph":"https://pith.science/api/pith-number/A5C6JEI7JSOZFKMIKRAL4QADRC/graph.json","fetch_events":"https://pith.science/api/pith-number/A5C6JEI7JSOZFKMIKRAL4QADRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5C6JEI7JSOZFKMIKRAL4QADRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5C6JEI7JSOZFKMIKRAL4QADRC/action/storage_attestation","attest_author":"https://pith.science/pith/A5C6JEI7JSOZFKMIKRAL4QADRC/action/author_attestation","sign_citation":"https://pith.science/pith/A5C6JEI7JSOZFKMIKRAL4QADRC/action/citation_signature","submit_replication":"https://pith.science/pith/A5C6JEI7JSOZFKMIKRAL4QADRC/action/replication_record"}},"created_at":"2026-07-05T10:30:49.375751+00:00","updated_at":"2026-07-05T10:30:49.375751+00:00"}